Metraipolis › archive › dc_656ca28ff425

CEFR Level Assessment across Languages and Text Granularities — arXiv:2610.41553

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41553
License (as archived): CC0-1.0
Archived: 2026-11-03T07:54:41.158Z
SHA-256 of the archived text: 157a676f8995fedbd9ae0fe682b14e8b4eb2d117a9fec2ea4cfb0fcbf1937517
Stable URL of this page: https://metraipolis.com/documento/dc_656ca28ff425

How to cite

CEFR Level Assessment across Languages and Text Granularities — arXiv:2610.41553 — arXiv (en), https://arxiv.org/abs/2610.41553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_656ca28ff425 (Metraipolis archive dc_656ca28ff425, sha256 157a676f8995fedbd9ae0fe682b14e8b4eb2d117a9fec2ea4cfb0fcbf1937517)

BibTeX

@misc{dc656ca28ff425,
  title = {CEFR Level Assessment across Languages and Text Granularities — arXiv:2610.41553},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41553},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_656ca28ff425; sha256 157a676f8995fedbd9ae0fe682b14e8b4eb2d117a9fec2ea4cfb0fcbf1937517},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatic assessment of textual CEFR levels is an important task in educational natural language processing. However, accurate CEFR level prediction remains challenging due to the naturally imbalanced distribution of CEFR levels and the ambiguous boundaries between adjacent levels. To address these challenges, we propose a unified training objective that combines focal loss with supervised contrastive learning. Focal loss mitigates class imbalance by emphasizing underrepresented and difficult examples, while supervised contrastive learning learns more discriminative representations by encouraging intra-class compactness and inter-class separation. We evaluate the proposed method on sentence- and document-level CEFR assessment in both monolingual and multilingual settings. Experimental results demonstrate that our method consistently outperforms strong baselines across all settings, establishing new state-of-the-art performance on multiple CEFR assessment benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41553 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:49:46.001Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).